INDEX

Explanations

numeric values and related symbols

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Numbers followed by zero

np_acts-logits-general · gemini-2.0-flash

technical data notations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

prechpartner

-0.62

opsida

-0.58

nocache

-0.58

المراجع

-0.57

toByteArray

-0.56

WebElementEntity

-0.55

')")

-0.55

})*/

-0.55

*/].

-0.54

Mutagenicity

-0.54

POSITIVE LOGITS

BagConstraints

0.67

 MainAxisSize

0.56

intree

0.52

URLException

0.48

 autorytatywna

0.47

存于互联网档案馆

0.47

drug

0.45

DrawerToggle

0.45

 fár

0.43

ままで

0.43

Activations Density 0.396%

numeric values and related symbols

Numbers followed by zero

technical data notations

No Comments

No Known Activations